Ollama's new app

2025-07-29 · Source: Ollama Blog · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering · Depth: Intermediate, quick

Summary

Ollama has launched a new desktop application for macOS and Windows, offering an easier way to interact with local language models. The app features drag-and-drop functionality for text and PDF files, enabling users to chat with documents and process code files for documentation, with an option to increase context length for larger documents. Leveraging Ollama's new multimodal engine, it also supports sending images to compatible models like Google DeepMind's Gemma 3, expanding its capabilities beyond text-only interactions.

Key takeaway

Ollama's new macOS/Windows app simplifies local LLM interaction, offering direct model download, chat, and multimodal support for models like Gemma 3. It enables drag-and-drop file processing for text/PDFs (with adjustable context requiring more memory) and code understanding, empowering desktop users with private, powerful AI for document analysis and complex reasoning.

Topics

• Ollama
• Local LLMs
• Multimodal AI
• Desktop Applications
• Document Processing

Best for: NLP Engineer, Computer Vision Engineer, Machine Learning Engineer, AI Engineer, Software Engineer

Related on AIssential

• Running local models on Macs gets faster with Ollama's MLX support — Ollama's MLX integration and NVFP4 support significantly enhance local LLM performance on Apple Silicon Macs.
• Running AI Models Locally with Ollama Completely Changed My AI Journey — Ollama simplifies running advanced AI models locally, enhancing privacy, speed, and experimentation without cloud dependency.
• Google announces Firebase Genkit with Ollama support — Firebase Genkit is an open-source framework for building and deploying AI apps, supporting local model execution via Ollama.
• Running Gemma 4 Locally with Ollama on Your PC — Gemma 4 offers open-weight, locally runnable LLMs with multimodal capabilities and diverse architectures for varied hardware.
• Tool support — Ollama now enables LLMs to interact with external tools for complex tasks via a new API feature.
• Codex + Ollama = Free Unlimited Coding AI — Ollama's integration with Codex enables free, local execution of open-source LLMs for AI coding tasks.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Ollama Blog.